Heat-aware toolpath reordering for 3D printing of physical parts

Patent metadata

Field	Value
Publication number	US-12521795-B2
Application number	US-202018001358-A
Country	US
Kind code	B2
Filing date	Jun 19, 2020
Priority date	Jun 19, 2020
Publication date	Jan 13, 2026
Grant date	Jan 13, 2026

Abstract

A computing system may include an access engine and a toolpath reordering engine. The access engine may be configured to access an original layer toolpath for slice of a 3D CAD object as well as a heat criticality measure for the original layer toolpath. The heat criticality measure may specify a heat impact for different points on the multiple toolpath segments of the original layer toolpath for the 3D printing of the physical part using the original layer toolpath. The toolpath reordering engine may be configured to reorder the multiple toolpath segments into a modified layer toolpath, and the modified layer toolpath may have a heat criticality measure with a lesser heat impact on the physical part than the heat criticality measure for the original layer toolpath.

First claim

The invention claimed is:

1 . A method comprising:
by a computing system: accessing an original layer toolpath for slice of a 3D CAD object, wherein the 3D CAD object represents a physical part, wherein the slice represents a physical layer for 3D printing of the physical part, and wherein the original layer toolpath controls the 3D printing of the physical layer and comprises a 3D print order for multiple toolpath segments for the original layer toolpath; accessing a heat criticality measure for the original layer toolpath, wherein the heat criticality measure for the original layer toolpath specifies a heat impact for different points on the multiple toolpath segments of the original layer toolpath for the 3D printing of the physical part using the 3D print order of original layer toolpath; reordering the multiple toolpath segments into a modified layer toolpath, wherein the modified layer toolpath has a different 3D print order from the original layer toolpath and has a heat criticality measure with a lesser heat impact on the physical part than the heat criticality measure for the original layer toolpath; and providing the modified layer toolpath to support the 3D printing of the physical part.

2 . The method of claim 1 , wherein the heat criticality measure for the original layer toolpath specifies a degree to which temperatures of the 3D part for each of the different points on the multiple toolpath segments exceed a critical temperature for the 3D printing of the physical part.

3 . The method of claim 1 , wherein reordering the multiple toolpath segments into the modified layer toolpath comprises iteratively optimizing candidate layer toolpaths using a path optimization algorithm applied to optimize the heat criticality measure and overall build time of the candidate layer toolpaths in order to determine the modified layer toolpath.

4 . The method of claim 3 , wherein iteratively optimizing the candidate layer toolpaths comprises, for a given iteration of the path optimization algorithm:
accessing, as a candidate layer toolpath, an output layer toolpath determined from a prior iteration of the path optimization algorithm, wherein the candidate layer toolpath comprises multiple toolpath segments; accessing a segment heat criticality measure for each of multiple toolpath segments of the candidate layer toolpath; applying, as the path optimization algorithm, an ant colony optimization algorithm in which a pheromone parameter of the ant colony optimization algorithm is specified as an inverse of the segment heat criticality measures; and determining, from the ant colony optimization algorithm, an output layer toolpath of a current iteration of the path optimization algorithm.

5 . The method of claim 4 , wherein the original layer toolpath is the candidate layer toolpath for an initial iteration of the path optimization algorithm.

6 . The method of claim 1 - or 2 , further comprising training a machine-learning model to determine the modified layer toolpath, including by:
configuring a parameterized reordering algorithm that accounts for multiple parameters in 3D printing of physical parts; providing, as inputs to the training, trial parameter values for the multiple parameters and an initial layer toolpath with a corresponding heat criticality measure; iterating, through the training, over candidate layer toolpaths with corresponding heat criticality measures to optimize the parameterized reordering algorithm based on the heat criticality measure and overall build time of the candidate layer toolpaths; and obtaining, from the iterating, the machine-learning model that designates learned parameter values for the multiple parameters.

7 . The method of claim 6 , wherein reordering the multiple toolpath segments into the modified layer toolpath comprises:
providing, as inputs to the machine-learning model, the original layer toolpath and the heat criticality measure for the original layer toolpath; and obtaining the modified layer toolpath as an output of the machine-learning model.

8 . A system comprising:
an access engine configured to:
access an original layer toolpath for slice of a 3D CAD object, wherein the 3D CAD object represents a physical part, wherein the slice represents a physical layer for 3D printing of the physical part, and wherein the original layer toolpath controls the 3D printing of the physical layer and comprises a 3D print order for multiple toolpath segments of the original layer toolpath; and
access a heat criticality measure for the original layer toolpath, wherein the heat criticality measure specifies a heat impact for different points on the multiple toolpath segments of the original layer toolpath for the 3D printing of the physical part using the original layer toolpath; and
a toolpath reordering engine configured to:
reorder the multiple toolpath segments into a modified layer toolpath, wherein the modified layer toolpath has a different 3D print order from the original layer toolpath and a heat criticality measure with a lesser heat impact on the physical part than the heat criticality measure for the original layer toolpath; and
provide the modified layer toolpath to support the 3D printing of the physical part.

9 . The system of claim 8 , wherein the heat criticality measure for the original layer toolpath specifies a degree to which temperatures of the 3D part for each of the different points on the multiple toolpath segments exceed a critical temperature for the 3D printing of the physical part.

10 . The system of claim 8 , wherein the toolpath reordering engine is configured to reorder the multiple toolpath segments into the modified layer toolpath by iteratively optimizing candidate layer toolpaths using a path optimization algorithm applied to optimize the heat criticality measure and overall build time of the candidate layer toolpaths in order to determine the modified layer toolpath.

11 . The system of claim 10 , wherein the toolpath reordering engine is configured to iteratively optimize the candidate layer toolpaths, including by, for a given iteration of the path optimization algorithm:
accessing, as a candidate layer toolpath, an output layer toolpath determined from a prior iteration of the path optimization algorithm, wherein the candidate layer toolpath comprises multiple toolpath segments; accessing a segment heat criticality measure for each of multiple toolpath segments of the candidate layer toolpath; applying, as the path optimization algorithm, an ant colony optimization algorithm in which a pheromone parameter of the ant colony optimization algorithm is specified as an inverse of the segment heat criticality measures; and determining, from the ant colony optimization algorithm, an output layer toolpath of a current iteration of the path optimization algorithm.

12 . The system of claim 11 , wherein the toolpath reordering engine is configured to identify the original layer toolpath as the candidate layer toolpath for an initial iteration of the path optimization algorithm.

13 . The system of claim 8 , wherein the toolpath reordering engine is further configured to train a machine learning model to determine the modified layer toolpath, including by:
configuring a parameterized reordering algorithm that accounts for multiple parameters in 3D printing of physical parts; providing, as inputs to the training, trial parameter values for the multiple parameters and an initial layer toolpath with a corresponding heat criticality measure; iterating, through the training, over candidate layer toolpaths with corresponding heat criticality measures to optim

Assignees

• Siemens Ind Software Inc

Inventors

• Eissing Katharina
• Fergani Omar
• Heinrichsdorff Frank
• Kastsian Darya
• Reznik Daniel

Classifications

• B22F10/366

  Scanning parameters, e.g. hatch distance or scanning strategy · CPC title

• B22F12/47

  parallel to the deposition plane · CPC title

• B22F12/44

  characterised by the configuration of the radiation means · CPC title

• B33Y50/02

  for controlling or regulating additive manufacturing processes · CPC title

• Y02P90/02

  Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS] · CPC title